It wouldnt let me bring the IPYNB file over and this is my first time posting a review so i didnt know how else to other than just copy pastaing that SoB right here.
import csv
ages =
sexes =
bmis =
children =
smoker_statuses =
regions =
charges =
with open(“insurance.csv”) as insurance_data_csv:
insurance_reader = csv.DictReader(insurance_data_csv)
for entry in insurance_reader:
ages.append(int(entry[“age”]))
sexes.append(entry[“sex”])
bmis.append(float(entry[“bmi”]))
children.append(int(entry[“children”]))
smoker_statuses.append(entry[“smoker”])
regions.append(entry[“region”])
charges.append(float(entry[“charges”]))
average_age = sum(ages) / len(ages)
print(average_age)
from collections import Counter
region_counter = Counter(regions)
most_common = region_counter.most_common(1)
print(f"Most common region: {most_common}")
smoker_charges = [charge for charge, smoker in zip(charges, smoker_statuses) if smoker == “yes”]
non_smoker_charges = [charge for charge, smoker in zip(charges, smoker_statuses) if smoker == “no”]
average_smoker_charges = sum(smoker_charges) / len(smoker_charges)
average_non_smoker_charges = sum(non_smoker_charges) / len(non_smoker_charges)
charge_difference = average_smoker_charges - average_non_smoker_charges
print(f"Average charges for smokers: {average_smoker_charges:.2f}“)
print(f"Average charges for non-smokers: {average_non_smoker_charges:.2f}”)
print(f"Difference in average charges between smokers and non-smokers: {charge_difference:.2f}")
ages_with_children = [age for age, child_count in zip(ages, children) if child_count >= 1]
average_age_with_children = sum(ages_with_children) / len(ages_with_children)
print(f"Average age for individuals with at least one child: {average_age_with_children:.2f}")
from collections import defaultdict
region_totals = defaultdict(float)
region_counts = defaultdict(int)
for region, charge in zip(regions, charges):
region_totals[region] += charge
region_counts[region] += 1
average_charges_by_region = {region: total / count for region, total, count in zip(region_totals.keys(), region_totals.values(), region_counts.values())}
most_expensive_region = max(average_charges_by_region, key=average_charges_by_region.get)
print(f"The most expensive region is {most_expensive_region} with an average charge of {average_charges_by_region[most_expensive_region]:.2f}")
